Pith. sign in

← back to paper

Review history

arxiv: 2508.05469 · 2 revisions

Let's Measure Information Step-by-Step: AI-Based Evaluation Beyond Vibes

  1. 2026-08-05 UNVERDICTED LOW v1.4.0-alltime-deepseek-medium novelty 6.0
    149224 ms 501 in 15784 out 2026-08-05T23:18:46.588233+00:00
  2. 2026-05-18 UNVERDICTED LOW v0.9.0 novelty 5.0
    26450 ms 5698 in 1463 out 2026-05-18T23:41:16.558764+00:00